Who came up with this FireTV PIN screen?

Full circle, text.

The weekend build: low cost and usable (sort of) local AI coding agent for people on a budget. Nvidia Tesla P40 (24GB), eGPU (Oculink) and a cheap mini PC (Intel N100). Running in VSCode via Ollama.

Ordered and looking forward

The AI model finally learned how to hit the ball, but it still has a long way to go. 🤖🕹️

I'm doing some AI training for the Duel of the Paddles game so it won't require two players to play. So far, after 250K+ steps (RL/PPO), it's still performing terribly. 😅🕹️🤖 #ai #artificalintelligence

There are some really points and thoughts by @aaronwhite in this "Who Will Win the Incumbent AI Battle?" video. piped.video/watch?v=X9SgohV6… #ai #artificialintelligence

I finally had a chance to rearrange my Pi5 cluster today. For the compute-only Pi5s (fan only, no USB/PCIe/NVMe), I got rid of the official Pi5 power supplies and replaced them with Anker PowerPort 6, which is common for Pi clusters. One of the reasons was that no matter what I did, the Pi5s didn't go beyond 9W of power consumption (3W idle). So, the official Pi5 power supply was overkill for my use case. Although the Anker PowerPort can handle 60W, I decided to be a good citizen and only connected 4 Pi5s to each unit, leaving plenty of extra overhead. By the way, they are connected to two different switches. 😅 While looking for some cables, I found my old AC Infinity fans, which I used to cool an Xbox. I thought, why not, and set them up to cool the power supplies. The fans have a thermal trigger, so they only run once the temperature goes beyond ~29°C/84F. By the way, I asked ChatGPT how to position the fans, and it suggested the push-pull configuration. I was skeptical at first, but it seems to work well. See the temperature in the image below. Let me know if there is a better way. Finally, I got these fancy USB-C cables that show the current power consumption. I like them and hope they last long enough since they are not cheap. 💸 P.S.: I'm still waiting for the official Raspberry Pi5 PoE HAT for my power-hungry Pi5s, which have NVMe disks. Let me know if you have any suggestions. #raspberrypi #pi5 #anker #usbc

I saw this variation of the pong game (link below) where two balls continuously move, aiming to capture the opposing player's area. My first question was how this game could end, if at all. I didn't see a possibility (correct me if I'm wrong) without modifying the game. So, I'm recreating the game with some changes: 1) Adding paddles so that players can directly control the balls, and 2) Introducing power-ups to give players an advantage. I have some ideas for power-ups, such as increasing the ball's speed every time it passes to the opposite player's paddle and hits the wall or giving an extra ball to the players when that occurs. I'm open to any suggestions and ideas. I'm counting on folks out there who lived through the '80s and '90s and played these kinds of games. You can find the original game at pong-wars.koenvangilst.nl And below is a screenshot from the game that I'm developing. #gaming #pong

Sharing the pictures of my old Macs for the Macintosh 40th Anniversary. Happy birthday Mac! #Apple #Mac #Macintosh

Single Pi5 performs ~65 embeddings/sec (including network overhead)

I don't have those scores. But each Pi5 serves around ~65 embeddings/sec (including network overhead)

Everything is handled by @nats_io Check out @thecodegangsta ‘s video at piped.video/byHGNUqIONw

For edge, I started with Terraform, which is my powerhouse, but it quickly became overkill. So, I switched to regular shell scripts. That being said, I recently watched a video by @synadia (piped.video/watch?v=EfxtiKMn…) and I'm thinking of switching to their approach as soon as they release it. For cloud, I'm using Fly.io, which hosts the multi-region NATS server and the public API server.

I haven't run any LLM yet. Although you can find some numbers from other people here on X. I used it for @embedefy See nitter.net/devfacet/status/174912… It can perform ~65 AI inference/sec with a single Pi 5 (including network overhead). But I'm also working on batch API to make it faster.

It can perform ~65 AI inference/sec with a single Pi 5 (including network overhead).

I’ve already tried some of them, the software support (e.g. Linux kernel) and system stability (Google it yourself) is no where near Raspberry Pi. They were keep crashing.

I guess it depends on what you are doing. In my case, I mostly work on embeddings/classification, and most of the models (huggingface.co/spaces/mteb/l…) are nicely utilized with Pi 5s. Currently, a single Pi 5 can handle approximately 65 requests per second (including traffic between the cloud and the cluster). I'm working on a batch API, so I'm hoping it will be much faster. Therefore, 16-core machines would be an overspend/underutilized in my case. The NATS server and the public API servers are set up for HA. They run in three different regions via Fly.io, and I only pay about $10 per month. If I lose power at home, for example, I can easily deploy it in the cloud temporarily (like active-passive), but I don't have an SLA with anyone, so it wouldn't be a problem to do nothing. That being said, I'm looking into solar solutions and secondary internet provider (maybe even Starlink) for temporary backup. Good questions 👍

This is how I save over $1000/mo on compute, storage, and bandwidth costs for my AI side projects: a total of 52 CPU cores, 104GB RAM, 3TB NVMe, unlimited ingress/egress, and less than 100W power consumption. The taller cluster runs API servers built with the Transformer.js library and the NATS services framework. The shorter cluster runs a Postgres database server (with streaming replication) and some services such as pgpool, prometheus, etc. They are all connected to the cloud via NATS using a secure WireGuard tunnel. No DNS server, no port forwarding, no load balancers. #raspberrypi #pi5 #AI #edge @nats_io @xenovacom @PineberryPi

My top 5 computer & programming books. What’s yours?

It’s a miracle… @QueenWillRock

My setup for classic real-time strategy game is coming along. It needs some decoration tho. #commandandconquer #redalert2

This brings back some good old memories. #quickshot 🕹

I hope it works

wow, it’s huge and sturdy. Fusion for ARM v8 by @mikroel

I've a function like (I'm open to a better solution):

My 7yo is calculating something very complicated. It might be related to space time continuum🖖

macOS Daemonology & Interprocess Communication with macOS #xpc #macOS Two much needed book for macOS.

Chapter 3 alone is worth it to buy this book 📕 “SwiftUI for Masterminds” by J.D Gauchat #SwiftUI #SwiftLang

The Art of WebAssembly by @battagline I really like the format of this book. Another nice one from @nostarch

Every time see a Go code without any comments. #golang

I didn’t know @billatnapier have this book until recently. It’s great and looking forward for the 2nd edition (up to date with his website). #crypto #cryptography

Need to check whether the given interface implements io.Seeker or not? #golang #code

Need io.TeeReader with limit? #golang #code

#golang #code Need to search byte slices in large files and streams?

“Tea, Earl Grey, Hot” I know someone who would appreciate it. But he needs to wait another 300+ years. #StarTrekTNG #StarTrekPicard

Although it’s focused on blockchains and cryptocurrencies, it’s a good reference book for cryptography. #cryptography #encryption #ellipticcurve

Here we go... “Serious Cryptography - A Practical Introduction to Modern Encryption” by @veorq #cryptography #encryption

Since I have the chance... Thank you so much for your performance despite the difficulties. These are from my collection and happy to have them.

That moment you decide to clean your laptop bag. #cables #adapters #usb

I got some @StarTrek pins from @FanSets and they look awesome. I really like Picard/Locutus (@SirPatStew) and Captain Janeway (@TheKateMulgrew) pins. #StarTrek #IDIC

You are my sunshine... Just now me and my 5yo sing together. Thank you @RobertPicardo and @JeriLRyan for creating such a scene. It’s one of my favorite moments of #StarTrekVoyager #StarTrek piped.video/watch?v=UBbWC7Z8…

The Linux Programming Interface by @mkerrisk - 1506 pages, probably the thickest book I have ever attempted to read. My feedback will take some time 😏 #linux

If you are thinking to learn C programming language then I recommend “The Little Book of C Programming” by @huwcol #cprogramming

High five to “The SiFive Learn Inventor” A RISC-V based development board: 150MHz, 512Kb flash, BLE, WiFi, 6x8 LEDs, 16KB instruction cache, and 64KB of SRAM. @SiFive @pimoroni @risc_v

A nice FPGA book for beginners by @simonmonk2 #fpga #verilog

I recently read RISC-V Assembly Language and The RISC-V Reader books. I highly recommend both. @risc_v #assembly

I’ve been waiting for this book. Thank you @petewarden and @dansitu #tinyml

The Art and Making of The Expanse @ExpanseOnPrime

My all time favorite character... Walter Bishop by John Noble #Fringe @thejohnnoble

@tgraf__ @danwendlandt : thanks for visiting the Mountain and great @ciliumproject presentation today. @Bose Auditorium

Super excited about Bose Frames. Amazing sound quality! @Bose #BoseFrames #BoseAR

Highly recommended - @intensivedata @martinkl

#startup #technical #debt @bhorowitz

Simple way to handle AWS credentials for ECS containers in a shell script #bash #sh #shell @awscloud